© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 99083
    Prev
    Next
    INDEX
    Explanations

    Christian or legal identity

    np_acts-logits-general · gemini-2.5-flash-lite

    museum, garden, domain, file, differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reasonable
    0.50
    Feb
    0.49
    ем
    0.49
    १
    0.48
    ิ่ง
    0.48
    ويم
    0.47
    中
    0.47
     obedient
    0.45
     Дело
    0.44
     Owned
    0.44
    POSITIVE LOGITS
     çap
    0.46
     alkot
    0.45
     değerlend
    0.45
     experimento
    0.44
     fotograf
    0.44
    䧉
    0.44
    =""><
    0.43
     blu
    0.42
     planar
    0.42
    ografia
    0.42
    Activations Density 0.000%

    No Known Activations